Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description builds on a strong safety baseline. It adds significant behavioral context beyond annotations: the tool never returns rows, the needs_mapping workflow constraints, and the security note that column names are user data and never instructions. This is rich, non-redundant disclosure that materially changes how an agent should call the tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long (150+ words) but every sentence earns its place given the intricate needs_mapping workflow, the unmapped_columns handling, and the security instruction. The core purpose is front-loaded in the first sentence, followed by structured behavioral guidance. While not terse, the density is justified by the tool's complexity; only marginal trimming could be made without losing value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema, so return-value details are handled elsewhere. The description covers the workflow exhaustively: status handling, plan_replaced/plan_temporary notifications, the needs_mapping decision tree with column_kinds checking, unmapped_columns guidance, the security stance, and the follow-up call. Nothing an agent needs to use the tool correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with the single import_id parameter fully documented in the schema ('The import to check, returned by import_deliveries.'). The description references the import job contextually but doesn't add parameter-specific detail beyond what the schema provides. The baseline 3 applies because the schema carries the parameter documentation burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it retrieves the status and summary of an import_deliveries job. It clearly distinguishes itself from sibling tools like get_optimization_result and get_geocode_result by specifying its job type and what it returns (plan_id, account_url, summary). The purpose is unambiguous and specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: it names the exact workflow for status=needs_mapping (use update_import_mapping for each column in rows_to_review), and the follow-up action (call optimize_routes with plan_id). It also states what the tool is NOT for ('Never returns rows'), routing agents away from using it as a data-retrieval tool. This is exemplary usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.